---
aliases:
  en:
  - attack policies
  - red-team attack policy
concept_id: attack_policy
preferred:
  en: attack policy
relations:
  relations:
    prerequisite:
    - control_evaluation
    related:
    - scheming
status: active
---

# attack policy

In a control evaluation, a red-team-constructed replacement for an untrusted model that is elicited, prompted, scaffolded, or trained to carry out a strategy for causing a specified unacceptable outcome while avoiding detection or shutdown, so that the protocol can be tested against adversarial model behavior.

## prerequisite

- [control evaluation](../terminology/control_evaluation.txt)

## related

- [scheming](../terminology/scheming.txt)

[Corpus index](../index.txt)